The Ricordi archive, a prestigious collection of significant musical manuscripts from renowned opera composers such as Donizetti, Verdi and Puccini, has been digitized. This process has allowed us to automatically extract samples that represent various musical elements depicted on the manuscripts, including notes, staves, clefs, erasures, and composer’s annotations, among others. To distinguish between digitization noise and actual music elements, a subset of these images was meticulously grouped and labeled by multiple individuals into several classes. After assessing the consistency of the annotations, we trained multiple neural network-based classifiers to differentiate between the identified music elements. The primary objective of this study was to evaluate the reliability of these classifiers, with the ultimate goal of using them for the automatic categorization of the remaining unannotated data set. The dataset, complemented by manual annotations, models, and source code used in these experiments are publicly accessible for replication purposes.

Optical Music Recognition in Manuscripts from the Ricordi Archive / F. Simonetta, R. Mondal, L.A. Ludovico, S. Ntalampiras (ACM INTERNATIONAL CONFERENCE PROCEEDINGS SERIES). - In: AM '24: Proceedings / [a cura di] L.A. Ludovico, D.A. Mauro. - [s.l] : ACM, 2024. - ISBN 9798400709685. - pp. 260-269 (( Intervento presentato al 19. convegno Audio Mostly Proceedings of the International Audio Mostly Conference: Explorations in Sonic Culture : 18 through 20 September tenutosi a Milano nel 2024 [10.1145/3678299.3678324].

Optical Music Recognition in Manuscripts from the Ricordi Archive

F. Simonetta
Primo
;
L.A. Ludovico
Penultimo
;
S. Ntalampiras
Ultimo
2024

Abstract

The Ricordi archive, a prestigious collection of significant musical manuscripts from renowned opera composers such as Donizetti, Verdi and Puccini, has been digitized. This process has allowed us to automatically extract samples that represent various musical elements depicted on the manuscripts, including notes, staves, clefs, erasures, and composer’s annotations, among others. To distinguish between digitization noise and actual music elements, a subset of these images was meticulously grouped and labeled by multiple individuals into several classes. After assessing the consistency of the annotations, we trained multiple neural network-based classifiers to differentiate between the identified music elements. The primary objective of this study was to evaluate the reliability of these classifiers, with the ultimate goal of using them for the automatic categorization of the remaining unannotated data set. The dataset, complemented by manual annotations, models, and source code used in these experiments are publicly accessible for replication purposes.
Computer Vision; Music; Neural Networks; Optical Music Recognition;
Settore INF/01 - Informatica
Settore INFO-01/A - Informatica
2024
Association for Computing Machinery (ACM)
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
_AudioMostly_2024__Optical_Music_Recognition_in_Manuscripts_from_the_Ricordi_Archive.pdf

accesso aperto

Descrizione: pdf
Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 2.83 MB
Formato Adobe PDF
2.83 MB Adobe PDF Visualizza/Apri
3678299.3678324.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 2.85 MB
Formato Adobe PDF
2.85 MB Adobe PDF Visualizza/Apri
2408.10260v1.pdf

accesso aperto

Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 2.85 MB
Formato Adobe PDF
2.85 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/1097049
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact